search_emails
AI agents call search_emails to retrieve information from MCP Outlook without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool searches emails, a retrieval operation with no side effects. Severity is medium rather than low because email search on a corporate account could expose sensitive business communications, financial details, or personal information if an agent performs broad or unintended searches. Confidence is 0.85 due to empty description, but naming convention and context strongly suggest a read-only query.
From the tool's definition Tool name 'search_emails' indicates querying/retrieving email data. Description is empty, but the sibling tools (get_inbox_emails, get_sent_emails, get_email_attachments) all retrieve data without modification, establishing this server's pattern of read…
Attacks that exploit this kind of access
search_emails. It is categorised as a Read tool in the MCP Outlook MCP Server, which means it retrieves data without modifying state.
Register the MCP Outlook MCP server in PolicyLayer and add a rule for search_emails: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches MCP Outlook. Nothing to install.
search_emails is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the search_emails rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for search_emails. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
search_emails is provided by the MCP Outlook MCP server (vince1024/outlook-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →